--- abstract: |- In this paper, we propose a model to develop robots’ covert perceptual capability using reinforcement learning. Covert perceptual behavior is treated as action selected by a motivational system. We apply this model to vision-based navigation. The goal is to enable a robot to learn road boundary type. Instead of dealing with problems in controlled environments with a low-dimensional state space, we test the model on images captured in non-stationary environments. Incremental Hierarchical Discriminant Regression is used to generate states on the fly. Its coarse-to-fine tree structure guarantees real-time retrieval in high-dimensional state space. K Nearest-Neighbor strategy is adopted to further reduce training time complexity. altloc: - http://asip.lucs.lu.se/ftp/pub/LUCS_Studies/LUCS123/huang.pdf - http://asip.lucs.lu.se/ftp/pub/LUCS_Studies/LUCS123/epirob05d.pdf chapter: ~ commentary: ~ commref: ~ confdates: 'July 22-24, 2005' conference: 'Fifth International Workshop on Epigenetic Robotics: Modeling Cognitive Development in Robotic Systems' confloc: 'Nara, Japan' contact_email: ~ creators_id: [] creators_name: - family: Huang given: Xiao honourific: '' lineage: '' - family: Weng given: Juyang honourific: '' lineage: '' date: 2005 date_type: published datestamp: 2006-07-23 department: ~ dir: disk0/00/00/49/81 edit_lock_since: ~ edit_lock_until: ~ edit_lock_user: ~ editors_id: [] editors_name: - family: Berthouze given: Luc honourific: '' lineage: '' - family: Kaplan given: Frédéric honourific: '' lineage: '' - family: Kozima given: Hideki honourific: '' lineage: '' - family: Yano given: Hiroyuki honourific: '' lineage: '' - family: Konczak given: Jürgen honourific: '' lineage: '' - family: Metta given: Giorgio honourific: '' lineage: '' - family: Nadel given: Jacqueline honourific: '' lineage: '' - family: Sandini given: Giulio honourific: '' lineage: '' - family: Stojanov given: Georgi honourific: '' lineage: '' - family: Balkenius given: Christian honourific: '' lineage: '' eprint_status: archive eprintid: 4981 fileinfo: /style/images/fileicons/application_pdf.png;/4981/1/huang.pdf full_text_status: public importid: ~ institution: ~ isbn: ~ ispublished: pub issn: ~ item_issues_comment: [] item_issues_count: 0 item_issues_description: [] item_issues_id: [] item_issues_reported_by: [] item_issues_resolved_by: [] item_issues_status: [] item_issues_timestamp: [] item_issues_type: [] keywords: 'vision-based navigation, incremental hierarchical discriminant regression, K-nearest neighbor Q-learning, developmental robot' lastmod: 2011-03-11 08:56:29 latitude: ~ longitude: ~ metadata_visibility: show note: ~ number: ~ pagerange: 107-110 pubdom: FALSE publication: ~ publisher: Lund University Cognitive Studies refereed: TRUE referencetext: ~ relation_type: [] relation_uri: [] reportno: ~ rev_number: 12 series: ~ source: ~ status_changed: 2007-09-12 17:05:42 subjects: - comp-sci-stat-model - comp-sci-mach-learn - comp-sci-robot succeeds: ~ suggestions: ~ sword_depositor: ~ sword_slug: ~ thesistype: ~ title: Covert Perceptual Capability Development type: confpaper userid: 3507 volume: 123